Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Enhancement of binary QSAR analysis by a GA-based variable selection method.

Hua Gao1, Michael S Lajiness, John Van Drie

  • 1Computer-Aided Drug Discovery, Pharmacia, Kalamazoo, MI 49007, USA. hua.gao@pharmacia.com

Journal of Molecular Graphics & Modelling
|February 23, 2002
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Prelnc2: A prediction tool for lncRNAs with enhanced multi-level features of RNAs.

PloS one·2023
Same author

Changes in the VOC of Fruits at Different Refrigeration Stages of 'Ruixue' and the Participation of Carboxylesterase <i>MdCXE20</i> in the Catabolism of Volatile Esters.

Foods (Basel, Switzerland)·2023
Same author

Synthesis of Aminoalkyl Sclareolide Derivatives and Antifungal Activity Studies.

Molecules (Basel, Switzerland)·2023
Same author

Filamentous Fungi-Derived Orsellinic Acid-Sesquiterpene Meroterpenoids: Fungal Sources, Chemical Structures, Bioactivities, and Biosynthesis.

Planta medica·2023
Same author

Automatic Thoughts, Self-Stigma, and Resilience Among Schizophrenia Patients with Metabolic Syndrome: A Cross-Sectional Study.

Neuropsychiatric disease and treatment·2023
Same author

Effects of femtosecond laser-assisted minimally invasive lamellar keratoplasty (FL-MILK) on mild-to-moderate and advanced keratoconus.

Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie·2023
Same journal

Halide-encapsulated C<sub>24</sub> fullerenes as molecular redox hosts for alkali metals: A density functional theory study.

Journal of molecular graphics & modelling·2026
Same journal

Efficacy of Tinospora cordifolia bioactives as agonists of Smoothened (Smo) receptor to promote oligodendroglial lineage induction for remyelination-based therapy.

Journal of molecular graphics & modelling·2026
Same journal

Dynamic remodeling of USP28 by the selective inhibitor CAS-010: Insights from DFT and molecular dynamics simulations.

Journal of molecular graphics & modelling·2026
Same journal

Beyond the catalytic site: Voxilaprevir and Pasireotide as repurposed therapeutics for conformational inhibition of ADAR1.

Journal of molecular graphics & modelling·2026
Same journal

A mechanism-guided framework for prioritizing membrane-interaction anti-Vibrio peptides from peptidomics data.

Journal of molecular graphics & modelling·2026
Same journal

A multi-Level Study of 20S proteasome inhibitors: an integrated approach combining chemistry and Modelling.

Journal of molecular graphics & modelling·2026
See all related articles

A genetic algorithm effectively selects molecular descriptors for binary quantitative structure-activity relationship (QSAR) models. This approach aids in analyzing high-throughput screening data for drug discovery by predicting compound activity.

Area of Science:

  • Computational chemistry
  • Medicinal chemistry
  • Cheminformatics

Background:

  • Binary quantitative structure-activity relationship (QSAR) models analyze high-throughput screening (HTS) data by correlating compound structures with binary biological activity (active/inactive).
  • Effective QSAR model derivation relies on selecting optimal molecular descriptors that represent chemico-biological interactions.
  • Variable selection is crucial for building robust predictive QSAR models.

Purpose of the Study:

  • To evaluate the efficacy of a genetic algorithm (GA) as a variable selection method for binary QSAR analysis.
  • To apply the GA-based variable selection to diverse compound datasets, including estrogen receptor (ER) ligands, carbonic anhydrase II inhibitors, and monoamine oxidase (MAO) inhibitors.
  • To demonstrate the capability of GA in identifying predictive molecular descriptors from a large pool.

Related Experiment Videos

Main Methods:

  • Utilized a genetic algorithm (GA) for automated variable selection in binary QSAR modeling.
  • Applied the GA to a pool of 150 molecular descriptors.
  • Tested the methodology on three distinct biological targets: ER, carbonic anhydrase II, and MAO.

Main Results:

  • Predictive binary QSAR models were successfully developed for all three compound sets using the GA-based variable selection.
  • The GA identified a preferred set of molecular descriptors capable of capturing relevant chemico-biological interactions.
  • Models were achieved within a reasonable number of GA generations, indicating computational efficiency.

Conclusions:

  • Genetic algorithms are highly effective for variable selection in binary QSAR analysis.
  • The GA approach facilitates the development of predictive QSAR models from HTS data.
  • This method enhances the process of identifying potential drug candidates by optimizing descriptor selection.